| <!DOCTYPE HTML> |
| <html lang="de"> |
| <head> |
| <!-- Generated by javadoc (17) --> |
| <title>StringUtil (Apache OpenNLP Tools 2.3.3 API)</title> |
| <meta name="viewport" content="width=device-width, initial-scale=1"> |
| <meta http-equiv="Content-Type" content="text/html; charset=UTF-8"> |
| <meta name="description" content="declaration: package: opennlp.tools.util, class: StringUtil"> |
| <meta name="generator" content="javadoc/ClassWriterImpl"> |
| <link rel="stylesheet" type="text/css" href="../../../stylesheet.css" title="Style"> |
| <link rel="stylesheet" type="text/css" href="../../../script-dir/jquery-ui.min.css" title="Style"> |
| <link rel="stylesheet" type="text/css" href="../../../jquery-ui.overrides.css" title="Style"> |
| <script type="text/javascript" src="../../../script.js"></script> |
| <script type="text/javascript" src="../../../script-dir/jquery-3.6.1.min.js"></script> |
| <script type="text/javascript" src="../../../script-dir/jquery-ui.min.js"></script> |
| </head> |
| <body class="class-declaration-page"> |
| <script type="text/javascript">var evenRowColor = "even-row-color"; |
| var oddRowColor = "odd-row-color"; |
| var tableTab = "table-tab"; |
| var activeTableTab = "active-table-tab"; |
| var pathtoroot = "../../../"; |
| loadScripts(document, 'script');</script> |
| <noscript> |
| <div>JavaScript is disabled on your browser.</div> |
| </noscript> |
| <div class="flex-box"> |
| <header role="banner" class="flex-header"> |
| <nav role="navigation"> |
| <!-- ========= START OF TOP NAVBAR ======= --> |
| <div class="top-nav" id="navbar-top"> |
| <div class="skip-nav"><a href="#skip-navbar-top" title="Skip navigation links">Skip navigation links</a></div> |
| <ul id="navbar-top-firstrow" class="nav-list" title="Navigation"> |
| <li><a href="../../../index.html">Overview</a></li> |
| <li><a href="package-summary.html">Package</a></li> |
| <li class="nav-bar-cell1-rev">Class</li> |
| <li><a href="package-tree.html">Tree</a></li> |
| <li><a href="../../../deprecated-list.html">Deprecated</a></li> |
| <li><a href="../../../index-all.html">Index</a></li> |
| <li><a href="../../../help-doc.html#class">Help</a></li> |
| </ul> |
| </div> |
| <div class="sub-nav"> |
| <div> |
| <ul class="sub-nav-list"> |
| <li>Summary: </li> |
| <li>Nested | </li> |
| <li>Field | </li> |
| <li><a href="#constructor-summary">Constr</a> | </li> |
| <li><a href="#method-summary">Method</a></li> |
| </ul> |
| <ul class="sub-nav-list"> |
| <li>Detail: </li> |
| <li>Field | </li> |
| <li><a href="#constructor-detail">Constr</a> | </li> |
| <li><a href="#method-detail">Method</a></li> |
| </ul> |
| </div> |
| <div class="nav-list-search"><label for="search-input">SEARCH:</label> |
| <input type="text" id="search-input" value="search" disabled="disabled"> |
| <input type="reset" id="reset-button" value="reset" disabled="disabled"> |
| </div> |
| </div> |
| <!-- ========= END OF TOP NAVBAR ========= --> |
| <span class="skip-nav" id="skip-navbar-top"></span></nav> |
| </header> |
| <div class="flex-content"> |
| <main role="main"> |
| <!-- ======== START OF CLASS DATA ======== --> |
| <div class="header"> |
| <div class="sub-title"><span class="package-label-in-type">Package</span> <a href="package-summary.html">opennlp.tools.util</a></div> |
| <h1 title="Class StringUtil" class="title">Class StringUtil</h1> |
| </div> |
| <div class="inheritance" title="Inheritance Tree"><a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/Object.html" title="class or interface in java.lang" class="external-link">java.lang.Object</a> |
| <div class="inheritance">opennlp.tools.util.StringUtil</div> |
| </div> |
| <section class="class-description" id="class-description"> |
| <hr> |
| <div class="type-signature"><span class="modifiers">public class </span><span class="element-name type-name-label">StringUtil</span> |
| <span class="extends-implements">extends <a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/Object.html" title="class or interface in java.lang" class="external-link">Object</a></span></div> |
| </section> |
| <section class="summary"> |
| <ul class="summary-list"> |
| <!-- ======== CONSTRUCTOR SUMMARY ======== --> |
| <li> |
| <section class="constructor-summary" id="constructor-summary"> |
| <h2>Constructor Summary</h2> |
| <div class="caption"><span>Constructors</span></div> |
| <div class="summary-table two-column-summary"> |
| <div class="table-header col-first">Constructor</div> |
| <div class="table-header col-last">Description</div> |
| <div class="col-constructor-name even-row-color"><code><a href="#%3Cinit%3E()" class="member-name-link">StringUtil</a>()</code></div> |
| <div class="col-last even-row-color"> </div> |
| </div> |
| </section> |
| </li> |
| <!-- ========== METHOD SUMMARY =========== --> |
| <li> |
| <section class="method-summary" id="method-summary"> |
| <h2>Method Summary</h2> |
| <div id="method-summary-table"> |
| <div class="table-tabs" role="tablist" aria-orientation="horizontal"><button id="method-summary-table-tab0" role="tab" aria-selected="true" aria-controls="method-summary-table.tabpanel" tabindex="0" onkeydown="switchTab(event)" onclick="show('method-summary-table', 'method-summary-table', 3)" class="active-table-tab">All Methods</button><button id="method-summary-table-tab1" role="tab" aria-selected="false" aria-controls="method-summary-table.tabpanel" tabindex="-1" onkeydown="switchTab(event)" onclick="show('method-summary-table', 'method-summary-table-tab1', 3)" class="table-tab">Static Methods</button><button id="method-summary-table-tab4" role="tab" aria-selected="false" aria-controls="method-summary-table.tabpanel" tabindex="-1" onkeydown="switchTab(event)" onclick="show('method-summary-table', 'method-summary-table-tab4', 3)" class="table-tab">Concrete Methods</button></div> |
| <div id="method-summary-table.tabpanel" role="tabpanel"> |
| <div class="summary-table three-column-summary" aria-labelledby="method-summary-table-tab0"> |
| <div class="table-header col-first">Modifier and Type</div> |
| <div class="table-header col-second">Method</div> |
| <div class="table-header col-last">Description</div> |
| <div class="col-first even-row-color method-summary-table method-summary-table-tab1 method-summary-table-tab4"><code>static void</code></div> |
| <div class="col-second even-row-color method-summary-table method-summary-table-tab1 method-summary-table-tab4"><code><a href="#computeShortestEditScript(java.lang.String,java.lang.String,int%5B%5D%5B%5D,java.lang.StringBuffer)" class="member-name-link">computeShortestEditScript</a><wbr>(<a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/String.html" title="class or interface in java.lang" class="external-link">String</a> wordForm, |
| <a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/String.html" title="class or interface in java.lang" class="external-link">String</a> lemma, |
| int[][] distance, |
| <a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/StringBuffer.html" title="class or interface in java.lang" class="external-link">StringBuffer</a> permutations)</code></div> |
| <div class="col-last even-row-color method-summary-table method-summary-table-tab1 method-summary-table-tab4"> |
| <div class="block">Computes the Shortest Edit Script (SES) to convert a word into its lemma.</div> |
| </div> |
| <div class="col-first odd-row-color method-summary-table method-summary-table-tab1 method-summary-table-tab4"><code>static <a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/String.html" title="class or interface in java.lang" class="external-link">String</a></code></div> |
| <div class="col-second odd-row-color method-summary-table method-summary-table-tab1 method-summary-table-tab4"><code><a href="#decodeShortestEditScript(java.lang.String,java.lang.String)" class="member-name-link">decodeShortestEditScript</a><wbr>(<a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/String.html" title="class or interface in java.lang" class="external-link">String</a> wordForm, |
| <a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/String.html" title="class or interface in java.lang" class="external-link">String</a> permutations)</code></div> |
| <div class="col-last odd-row-color method-summary-table method-summary-table-tab1 method-summary-table-tab4"> |
| <div class="block">Reads the predicted Shortest Edit Script (SES) by a lemmatizer model and applies the |
| permutations to obtain the lemma from the <code>wordForm</code>.</div> |
| </div> |
| <div class="col-first even-row-color method-summary-table method-summary-table-tab1 method-summary-table-tab4"><code>static <a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/String.html" title="class or interface in java.lang" class="external-link">String</a></code></div> |
| <div class="col-second even-row-color method-summary-table method-summary-table-tab1 method-summary-table-tab4"><code><a href="#getShortestEditScript(java.lang.String,java.lang.String)" class="member-name-link">getShortestEditScript</a><wbr>(<a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/String.html" title="class or interface in java.lang" class="external-link">String</a> wordForm, |
| <a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/String.html" title="class or interface in java.lang" class="external-link">String</a> lemma)</code></div> |
| <div class="col-last even-row-color method-summary-table method-summary-table-tab1 method-summary-table-tab4"> </div> |
| <div class="col-first odd-row-color method-summary-table method-summary-table-tab1 method-summary-table-tab4"><code>static boolean</code></div> |
| <div class="col-second odd-row-color method-summary-table method-summary-table-tab1 method-summary-table-tab4"><code><a href="#isEmpty(java.lang.CharSequence)" class="member-name-link">isEmpty</a><wbr>(<a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/CharSequence.html" title="class or interface in java.lang" class="external-link">CharSequence</a> theString)</code></div> |
| <div class="col-last odd-row-color method-summary-table method-summary-table-tab1 method-summary-table-tab4"> </div> |
| <div class="col-first even-row-color method-summary-table method-summary-table-tab1 method-summary-table-tab4"><code>static boolean</code></div> |
| <div class="col-second even-row-color method-summary-table method-summary-table-tab1 method-summary-table-tab4"><code><a href="#isWhitespace(char)" class="member-name-link">isWhitespace</a><wbr>(char charCode)</code></div> |
| <div class="col-last even-row-color method-summary-table method-summary-table-tab1 method-summary-table-tab4"> |
| <div class="block">Determines if the specified <a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/Character.html" title="class or interface in java.lang" class="external-link"><code>Character</code></a> is a whitespace.</div> |
| </div> |
| <div class="col-first odd-row-color method-summary-table method-summary-table-tab1 method-summary-table-tab4"><code>static boolean</code></div> |
| <div class="col-second odd-row-color method-summary-table method-summary-table-tab1 method-summary-table-tab4"><code><a href="#isWhitespace(int)" class="member-name-link">isWhitespace</a><wbr>(int charCode)</code></div> |
| <div class="col-last odd-row-color method-summary-table method-summary-table-tab1 method-summary-table-tab4"> |
| <div class="block">Determines if the specified <a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/Character.html" title="class or interface in java.lang" class="external-link"><code>Character</code></a> is a whitespace.</div> |
| </div> |
| <div class="col-first even-row-color method-summary-table method-summary-table-tab1 method-summary-table-tab4"><code>static int[][]</code></div> |
| <div class="col-second even-row-color method-summary-table method-summary-table-tab1 method-summary-table-tab4"><code><a href="#levenshteinDistance(java.lang.String,java.lang.String)" class="member-name-link">levenshteinDistance</a><wbr>(<a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/String.html" title="class or interface in java.lang" class="external-link">String</a> wordForm, |
| <a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/String.html" title="class or interface in java.lang" class="external-link">String</a> lemma)</code></div> |
| <div class="col-last even-row-color method-summary-table method-summary-table-tab1 method-summary-table-tab4"> |
| <div class="block">Computes the <i>Levenshtein</i> distance of two strings in a matrix.</div> |
| </div> |
| <div class="col-first odd-row-color method-summary-table method-summary-table-tab1 method-summary-table-tab4"><code>static <a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/String.html" title="class or interface in java.lang" class="external-link">String</a></code></div> |
| <div class="col-second odd-row-color method-summary-table method-summary-table-tab1 method-summary-table-tab4"><code><a href="#toLowerCase(java.lang.CharSequence)" class="member-name-link">toLowerCase</a><wbr>(<a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/CharSequence.html" title="class or interface in java.lang" class="external-link">CharSequence</a> string)</code></div> |
| <div class="col-last odd-row-color method-summary-table method-summary-table-tab1 method-summary-table-tab4"> |
| <div class="block">Converts a <a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/CharSequence.html" title="class or interface in java.lang" class="external-link"><code>CharSequence</code></a> to lower case, independent of the current |
| <a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/util/Locale.html" title="class or interface in java.util" class="external-link"><code>Locale</code></a> via <a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/Character.html#toLowerCase(int)" title="class or interface in java.lang" class="external-link"><code>Character.toLowerCase(int)</code></a> which uses |
| mapping information from the UnicodeData file.</div> |
| </div> |
| <div class="col-first even-row-color method-summary-table method-summary-table-tab1 method-summary-table-tab4"><code>static <a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/nio/CharBuffer.html" title="class or interface in java.nio" class="external-link">CharBuffer</a></code></div> |
| <div class="col-second even-row-color method-summary-table method-summary-table-tab1 method-summary-table-tab4"><code><a href="#toLowerCaseCharBuffer(java.lang.CharSequence)" class="member-name-link">toLowerCaseCharBuffer</a><wbr>(<a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/CharSequence.html" title="class or interface in java.lang" class="external-link">CharSequence</a> sequence)</code></div> |
| <div class="col-last even-row-color method-summary-table method-summary-table-tab1 method-summary-table-tab4"> </div> |
| <div class="col-first odd-row-color method-summary-table method-summary-table-tab1 method-summary-table-tab4"><code>static <a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/String.html" title="class or interface in java.lang" class="external-link">String</a></code></div> |
| <div class="col-second odd-row-color method-summary-table method-summary-table-tab1 method-summary-table-tab4"><code><a href="#toUpperCase(java.lang.CharSequence)" class="member-name-link">toUpperCase</a><wbr>(<a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/CharSequence.html" title="class or interface in java.lang" class="external-link">CharSequence</a> string)</code></div> |
| <div class="col-last odd-row-color method-summary-table method-summary-table-tab1 method-summary-table-tab4"> |
| <div class="block">Converts a <a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/CharSequence.html" title="class or interface in java.lang" class="external-link"><code>CharSequence</code></a> to upper case, independent of the current |
| <a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/util/Locale.html" title="class or interface in java.util" class="external-link"><code>Locale</code></a> via <a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/Character.html#toUpperCase(int)" title="class or interface in java.lang" class="external-link"><code>Character.toUpperCase(char)</code></a> which uses |
| mapping information from the UnicodeData file.</div> |
| </div> |
| </div> |
| </div> |
| </div> |
| <div class="inherited-list"> |
| <h3 id="methods-inherited-from-class-java.lang.Object">Methods inherited from class java.lang.<a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/Object.html" title="class or interface in java.lang" class="external-link">Object</a></h3> |
| <code><a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/Object.html#equals(java.lang.Object)" title="class or interface in java.lang" class="external-link">equals</a>, <a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/Object.html#getClass()" title="class or interface in java.lang" class="external-link">getClass</a>, <a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/Object.html#hashCode()" title="class or interface in java.lang" class="external-link">hashCode</a>, <a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/Object.html#notify()" title="class or interface in java.lang" class="external-link">notify</a>, <a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/Object.html#notifyAll()" title="class or interface in java.lang" class="external-link">notifyAll</a>, <a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/Object.html#toString()" title="class or interface in java.lang" class="external-link">toString</a>, <a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/Object.html#wait()" title="class or interface in java.lang" class="external-link">wait</a>, <a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/Object.html#wait(long)" title="class or interface in java.lang" class="external-link">wait</a>, <a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/Object.html#wait(long,int)" title="class or interface in java.lang" class="external-link">wait</a></code></div> |
| </section> |
| </li> |
| </ul> |
| </section> |
| <section class="details"> |
| <ul class="details-list"> |
| <!-- ========= CONSTRUCTOR DETAIL ======== --> |
| <li> |
| <section class="constructor-details" id="constructor-detail"> |
| <h2>Constructor Details</h2> |
| <ul class="member-list"> |
| <li> |
| <section class="detail" id="<init>()"> |
| <h3>StringUtil</h3> |
| <div class="member-signature"><span class="modifiers">public</span> <span class="element-name">StringUtil</span>()</div> |
| </section> |
| </li> |
| </ul> |
| </section> |
| </li> |
| <!-- ============ METHOD DETAIL ========== --> |
| <li> |
| <section class="method-details" id="method-detail"> |
| <h2>Method Details</h2> |
| <ul class="member-list"> |
| <li> |
| <section class="detail" id="isWhitespace(char)"> |
| <h3>isWhitespace</h3> |
| <div class="member-signature"><span class="modifiers">public static</span> <span class="return-type">boolean</span> <span class="element-name">isWhitespace</span><wbr><span class="parameters">(char charCode)</span></div> |
| <div class="block">Determines if the specified <a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/Character.html" title="class or interface in java.lang" class="external-link"><code>Character</code></a> is a whitespace. |
| A character is considered a whitespace when one of the following conditions is met: |
| <ul> |
| <li>It's a <a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/Character.html#isWhitespace(int)" title="class or interface in java.lang" class="external-link"><code>Character.isWhitespace(int)</code></a> whitespace.</li> |
| <li>It's a part of the Unicode Zs category (<a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/Character.html#SPACE_SEPARATOR" title="class or interface in java.lang" class="external-link"><code>Character.SPACE_SEPARATOR</code></a>).</li> |
| </ul> |
| |
| <a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/Character.html#isWhitespace(int)" title="class or interface in java.lang" class="external-link"><code>Character.isWhitespace(int)</code></a> does not include no-break spaces. |
| In OpenNLP no-break spaces are also considered as white spaces.</div> |
| <dl class="notes"> |
| <dt>Parameters:</dt> |
| <dd><code>charCode</code> - The character to check.</dd> |
| <dt>Returns:</dt> |
| <dd><code>true</code> if <code>charCode</code> represents a white space, <code>false</code> otherwise.</dd> |
| </dl> |
| </section> |
| </li> |
| <li> |
| <section class="detail" id="isWhitespace(int)"> |
| <h3>isWhitespace</h3> |
| <div class="member-signature"><span class="modifiers">public static</span> <span class="return-type">boolean</span> <span class="element-name">isWhitespace</span><wbr><span class="parameters">(int charCode)</span></div> |
| <div class="block">Determines if the specified <a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/Character.html" title="class or interface in java.lang" class="external-link"><code>Character</code></a> is a whitespace. |
| A character is considered a whitespace when one of the following conditions is met: |
| |
| <ul> |
| <li>Its a <a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/Character.html#isWhitespace(int)" title="class or interface in java.lang" class="external-link"><code>Character.isWhitespace(int)</code></a> whitespace.</li> |
| <li>Its a part of the Unicode Zs category (<a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/Character.html#SPACE_SEPARATOR" title="class or interface in java.lang" class="external-link"><code>Character.SPACE_SEPARATOR</code></a>).</li> |
| </ul> |
| |
| <a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/Character.html#isWhitespace(int)" title="class or interface in java.lang" class="external-link"><code>Character.isWhitespace(int)</code></a> does not include no-break spaces. |
| In OpenNLP no-break spaces are also considered as white spaces.</div> |
| <dl class="notes"> |
| <dt>Parameters:</dt> |
| <dd><code>charCode</code> - An int representation of a character to check.</dd> |
| <dt>Returns:</dt> |
| <dd><code>true</code> if <code>charCode</code> represents a white space, <code>false</code> otherwise.</dd> |
| </dl> |
| </section> |
| </li> |
| <li> |
| <section class="detail" id="toLowerCase(java.lang.CharSequence)"> |
| <h3>toLowerCase</h3> |
| <div class="member-signature"><span class="modifiers">public static</span> <span class="return-type"><a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/String.html" title="class or interface in java.lang" class="external-link">String</a></span> <span class="element-name">toLowerCase</span><wbr><span class="parameters">(<a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/CharSequence.html" title="class or interface in java.lang" class="external-link">CharSequence</a> string)</span></div> |
| <div class="block">Converts a <a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/CharSequence.html" title="class or interface in java.lang" class="external-link"><code>CharSequence</code></a> to lower case, independent of the current |
| <a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/util/Locale.html" title="class or interface in java.util" class="external-link"><code>Locale</code></a> via <a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/Character.html#toLowerCase(int)" title="class or interface in java.lang" class="external-link"><code>Character.toLowerCase(int)</code></a> which uses |
| mapping information from the UnicodeData file.</div> |
| <dl class="notes"> |
| <dt>Parameters:</dt> |
| <dd><code>string</code> - The <a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/CharSequence.html" title="class or interface in java.lang" class="external-link"><code>CharSequence</code></a> to transform.</dd> |
| <dt>Returns:</dt> |
| <dd>The lower-cased String.</dd> |
| </dl> |
| </section> |
| </li> |
| <li> |
| <section class="detail" id="toLowerCaseCharBuffer(java.lang.CharSequence)"> |
| <h3>toLowerCaseCharBuffer</h3> |
| <div class="member-signature"><span class="modifiers">public static</span> <span class="return-type"><a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/nio/CharBuffer.html" title="class or interface in java.nio" class="external-link">CharBuffer</a></span> <span class="element-name">toLowerCaseCharBuffer</span><wbr><span class="parameters">(<a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/CharSequence.html" title="class or interface in java.lang" class="external-link">CharSequence</a> sequence)</span></div> |
| </section> |
| </li> |
| <li> |
| <section class="detail" id="toUpperCase(java.lang.CharSequence)"> |
| <h3>toUpperCase</h3> |
| <div class="member-signature"><span class="modifiers">public static</span> <span class="return-type"><a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/String.html" title="class or interface in java.lang" class="external-link">String</a></span> <span class="element-name">toUpperCase</span><wbr><span class="parameters">(<a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/CharSequence.html" title="class or interface in java.lang" class="external-link">CharSequence</a> string)</span></div> |
| <div class="block">Converts a <a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/CharSequence.html" title="class or interface in java.lang" class="external-link"><code>CharSequence</code></a> to upper case, independent of the current |
| <a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/util/Locale.html" title="class or interface in java.util" class="external-link"><code>Locale</code></a> via <a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/Character.html#toUpperCase(int)" title="class or interface in java.lang" class="external-link"><code>Character.toUpperCase(char)</code></a> which uses |
| mapping information from the UnicodeData file.</div> |
| <dl class="notes"> |
| <dt>Parameters:</dt> |
| <dd><code>string</code> - The <a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/CharSequence.html" title="class or interface in java.lang" class="external-link"><code>CharSequence</code></a> to transform.</dd> |
| <dt>Returns:</dt> |
| <dd>The upper-cased String</dd> |
| </dl> |
| </section> |
| </li> |
| <li> |
| <section class="detail" id="isEmpty(java.lang.CharSequence)"> |
| <h3>isEmpty</h3> |
| <div class="member-signature"><span class="modifiers">public static</span> <span class="return-type">boolean</span> <span class="element-name">isEmpty</span><wbr><span class="parameters">(<a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/CharSequence.html" title="class or interface in java.lang" class="external-link">CharSequence</a> theString)</span></div> |
| <dl class="notes"> |
| <dt>Returns:</dt> |
| <dd><code>true</code> if <a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/CharSequence.html#length()" title="class or interface in java.lang" class="external-link"><code>CharSequence.length()</code></a> is <code>0</code> or <code>null</code>, otherwise |
| <code>false</code></dd> |
| <dt>Since:</dt> |
| <dd>1.5.1</dd> |
| </dl> |
| </section> |
| </li> |
| <li> |
| <section class="detail" id="levenshteinDistance(java.lang.String,java.lang.String)"> |
| <h3>levenshteinDistance</h3> |
| <div class="member-signature"><span class="modifiers">public static</span> <span class="return-type">int[][]</span> <span class="element-name">levenshteinDistance</span><wbr><span class="parameters">(<a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/String.html" title="class or interface in java.lang" class="external-link">String</a> wordForm, |
| <a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/String.html" title="class or interface in java.lang" class="external-link">String</a> lemma)</span></div> |
| <div class="block">Computes the <i>Levenshtein</i> distance of two strings in a matrix. |
| <p> |
| Based on this |
| <a href="https://en.wikipedia.org/wiki/Levenshtein_distance#Computing_Levenshtein_distance"> |
| pseudo-code</a> which in turn is based on the paper Wagner, Robert A.; Fischer, Michael J. (1974), |
| "The String-to-String Correction Problem", Journal of the ACM 21 (1): 168-173</div> |
| <dl class="notes"> |
| <dt>Parameters:</dt> |
| <dd><code>wordForm</code> - The form as input.</dd> |
| <dd><code>lemma</code> - The target lemma.</dd> |
| <dt>Returns:</dt> |
| <dd>A 2-dimensional Levenshtein distance matrix.</dd> |
| </dl> |
| </section> |
| </li> |
| <li> |
| <section class="detail" id="computeShortestEditScript(java.lang.String,java.lang.String,int[][],java.lang.StringBuffer)"> |
| <h3>computeShortestEditScript</h3> |
| <div class="member-signature"><span class="modifiers">public static</span> <span class="return-type">void</span> <span class="element-name">computeShortestEditScript</span><wbr><span class="parameters">(<a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/String.html" title="class or interface in java.lang" class="external-link">String</a> wordForm, |
| <a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/String.html" title="class or interface in java.lang" class="external-link">String</a> lemma, |
| int[][] distance, |
| <a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/StringBuffer.html" title="class or interface in java.lang" class="external-link">StringBuffer</a> permutations)</span></div> |
| <div class="block">Computes the Shortest Edit Script (SES) to convert a word into its lemma. |
| This is based on Chrupala's PhD thesis (2008).</div> |
| <dl class="notes"> |
| <dt>Parameters:</dt> |
| <dd><code>wordForm</code> - The token.</dd> |
| <dd><code>lemma</code> - The target lemma.</dd> |
| <dd><code>distance</code> - A 2-dimensional Levenshtein distance matrix.</dd> |
| <dd><code>permutations</code> - The number of permutations.</dd> |
| </dl> |
| </section> |
| </li> |
| <li> |
| <section class="detail" id="decodeShortestEditScript(java.lang.String,java.lang.String)"> |
| <h3>decodeShortestEditScript</h3> |
| <div class="member-signature"><span class="modifiers">public static</span> <span class="return-type"><a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/String.html" title="class or interface in java.lang" class="external-link">String</a></span> <span class="element-name">decodeShortestEditScript</span><wbr><span class="parameters">(<a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/String.html" title="class or interface in java.lang" class="external-link">String</a> wordForm, |
| <a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/String.html" title="class or interface in java.lang" class="external-link">String</a> permutations)</span></div> |
| <div class="block">Reads the predicted Shortest Edit Script (SES) by a lemmatizer model and applies the |
| permutations to obtain the lemma from the <code>wordForm</code>.</div> |
| <dl class="notes"> |
| <dt>Parameters:</dt> |
| <dd><code>wordForm</code> - The wordForm as input.</dd> |
| <dd><code>permutations</code> - The permutations predicted by the lemmatizer model.</dd> |
| <dt>Returns:</dt> |
| <dd>The decoded lemma.</dd> |
| </dl> |
| </section> |
| </li> |
| <li> |
| <section class="detail" id="getShortestEditScript(java.lang.String,java.lang.String)"> |
| <h3>getShortestEditScript</h3> |
| <div class="member-signature"><span class="modifiers">public static</span> <span class="return-type"><a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/String.html" title="class or interface in java.lang" class="external-link">String</a></span> <span class="element-name">getShortestEditScript</span><wbr><span class="parameters">(<a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/String.html" title="class or interface in java.lang" class="external-link">String</a> wordForm, |
| <a href="https://docs.oracle.com/en/java/javase/17/docs/api/java.base/java/lang/String.html" title="class or interface in java.lang" class="external-link">String</a> lemma)</span></div> |
| <dl class="notes"> |
| <dt>Parameters:</dt> |
| <dd><code>wordForm</code> - The word as input.</dd> |
| <dd><code>lemma</code> - The target lemma.</dd> |
| <dt>Returns:</dt> |
| <dd>Retrieves the Shortest Edit Script (SES) required to go from a word to a lemma.</dd> |
| </dl> |
| </section> |
| </li> |
| </ul> |
| </section> |
| </li> |
| </ul> |
| </section> |
| <!-- ========= END OF CLASS DATA ========= --> |
| </main> |
| <footer role="contentinfo"> |
| <hr> |
| <p class="legal-copy"><small>Copyright © 2023 <a href="https://www.apache.org/">The Apache Software Foundation</a>. All rights reserved.</small></p> |
| </footer> |
| </div> |
| </div> |
| </body> |
| </html> |